Summary
Amogh Adishesha is an applied scientist with 8 years of experience building multimodal generative models, currently advancing long-form video diffusion and efficient alignment architectures as a Member of Technical Staff. He combines a PhD in Informatics with hands-on product work—shipping lip-sync, speaker-separation, parametric talking-head, and large diffusion transformer models for consumer-facing video at Mirage and now Odyssey. His academic work improved biomedical imaging pipelines via novel Poisson-Gaussian loss formulations and transformer-based denoisers, boosting Micro-CT throughput and downstream analyses. Known for bridging research and production, he has interned at Microsoft and Outward where he contributed to large-scale text-to-image and novel-view synthesis efforts that informed commercial deployments. Colleagues rely on him for pragmatic, data-specific model design that spans audio, text, pose and image conditioning across challenging real-world modalities.
8 years of coding experience
7 years of employment as a software developer
Bachelor’s Degree Electrical Electronics and Communications Engineering, Bachelor’s Degree Electrical Electronics and Communications Engineering at Visvesvaraya Technological University
Doctor of Philosophy - PhD Informatics, Doctor of Philosophy - PhD Informatics at Penn State University
High School CBSE, High School CBSE at Sri Sankara Senior Secondary School
Kannada, Hindi, Tamil, French, English